notebook.community

Edit and run

network_df

  1. article-level (single network) statistics
  2. out = network_df.csv
  3. calculation notes below




In [1]:



    


import networkx as nx
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline
import os
from glob import glob

pd.set_option('display.mpl_style', 'default') 
# display all the columns
pd.set_option('display.width', 5000) 
pd.set_option('display.max_columns', 60)

gml_files = glob('../output/network/*/*.gml')



    











In [2]:



    


def calculate_graph_inf(graph):
    graph.name = filename
    info = nx.info(graph)
    print info
    #plot spring layout
    #plt.figure(figsize=(10,10))
    #nx.draw_spring(graph, arrows=True, with_labels=True)

def highest_centrality(cent_dict):
    """Returns a tuple (node,value) with the node
    with largest value from centrality dictionary."""
    # create ordered tuple of centrality data
    cent_items = [(b,a) for (a,b) in cent_dict.iteritems()]
    # sort in descending order
    cent_items.sort()
    cent_items.reverse()
    return tuple(reversed(cent_items[0]))



    











In [3]:



    


# create empty dataframe with columns

network_data_columns = ['name',
                    'sentiment',
                    'n nodes',
                    'n edges',
                    'avg degree',
                    'density',
                    'avg deg cent',
                    'avg bet cent',
                    'avg clo cent',
                    'highest degc',
                    'highest betc',
                    'highest cloc',
                    'avg node connect',
                    'deg assort coeff',
                    'avg in-deg',
                    'avg out-deg',
                    'n strong comp',
                    'n weak comp',
                    'n conn comp',
                    'Gc size'
                    ]

network_data = pd.DataFrame(columns = network_data_columns)



    











In [4]:



    


# graph = directed, ugraph = undirected

for graph_num, gml_graph in enumerate(gml_files):
    graph = nx.read_gml(gml_graph)
    ugraph = graph.to_undirected() ## to undirected graph
    ## adding those missing edges back
    U = graph.to_undirected(reciprocal=True)
    e = U.edges()
    ugraph.add_edges_from(e)
    ##
    (filepath, filename) = os.path.split(gml_graph)
    print('-' * 40)
    print(gml_graph)
    calculate_graph_inf(graph)
    #calculate_graph_inf(ugraph)

    # calculate variables
    
    sent = filepath.split('/')[-1]
    nodes = nx.number_of_nodes(graph)
    edges = nx.number_of_edges(graph)
    density = float("{0:.4f}".format(nx.density(graph)))
    avg_deg_cen = np.array(nx.degree_centrality(graph).values()).mean()
    avg_bet_cen = np.array(nx.betweenness_centrality(graph).values()).mean()
    avg_clo_cen = np.array(nx.closeness_centrality(graph).values()).mean()
    in_deg = sum(graph.in_degree().values())/float(nx.number_of_nodes(graph))
    out_deg = sum(graph.out_degree().values())/float(nx.number_of_nodes(graph))
    avg_deg = float("{0:.4f}".format(in_deg + out_deg))
    strong_comp = nx.number_strongly_connected_components(graph)
    weak_comp =  nx.number_weakly_connected_components(graph)
    avg_node_con = float("{0:.4f}".format((nx.average_node_connectivity(graph))))
    deg_assort_coeff = float("{0:.4f}".format((nx.degree_assortativity_coefficient(graph))))
    conn_comp = nx.number_connected_components(ugraph)
    deg_cen = nx.degree_centrality(graph)
    bet_cen = nx.betweenness_centrality(graph)
    clo_cen = nx.closeness_centrality(graph)
    highest_deg_cen = highest_centrality(deg_cen)
    highest_bet_cen = highest_centrality(bet_cen)
    highest_clo_cen = highest_centrality(clo_cen)
    Gc = len(max(nx.connected_component_subgraphs(ugraph), key=len))

    # save variables into list

    graph_values = {'name':filename,
                    'sentiment':sent,
                    'n nodes':nodes,
                    'n edges':edges,
                    'avg degree':avg_deg,
                    'density':density,
                    'avg deg cent':"%.4f" % avg_deg_cen,
                    'avg bet cent':"%.4f" % avg_bet_cen,
                    'avg clo cent':"%.4f" % avg_clo_cen,
                    'highest degc':highest_deg_cen,
                    'highest betc':highest_bet_cen,
                    'highest cloc':highest_clo_cen,
                    'avg node connect':avg_node_con,
                    'deg assort coeff':deg_assort_coeff,
                    'avg in-deg':"%.4f" % in_deg,
                    'avg out-deg':"%.4f" % out_deg,
                    'n strong comp':strong_comp,
                    'n weak comp':weak_comp,
                    'n conn comp':conn_comp,
                    'Gc size':Gc
                    }
    
    network_data = network_data.append(graph_values, ignore_index=True)
    
#    if graph_num == 0:
#        break



    


















    






----------------------------------------
../output/network/negative/article03.gml
Name: article03.gml
Type: MultiDiGraph
Number of nodes: 18
Number of edges: 13
Average in degree:   0.7222
Average out degree:   0.7222
----------------------------------------
../output/network/negative/article05.gml
Name: article05.gml
Type: MultiDiGraph
Number of nodes: 22
Number of edges: 25
Average in degree:   1.1364
Average out degree:   1.1364
----------------------------------------
../output/network/negative/article06.gml
Name: article06.gml
Type: MultiDiGraph
Number of nodes: 124
Number of edges: 121
Average in degree:   0.9758
Average out degree:   0.9758
----------------------------------------
../output/network/negative/article07.gml
Name: article07.gml
Type: MultiDiGraph
Number of nodes: 56
Number of edges: 57
Average in degree:   1.0179
Average out degree:   1.0179
----------------------------------------
../output/network/negative/article1.gml
Name: article1.gml
Type: MultiDiGraph
Number of nodes: 140
Number of edges: 147
Average in degree:   1.0500
Average out degree:   1.0500
----------------------------------------
../output/network/negative/article1001.gml
Name: article1001.gml
Type: MultiDiGraph
Number of nodes: 134
Number of edges: 134
Average in degree:   1.0000
Average out degree:   1.0000
----------------------------------------
../output/network/negative/article1021.gml
Name: article1021.gml
Type: MultiDiGraph
Number of nodes: 64
Number of edges: 64
Average in degree:   1.0000
Average out degree:   1.0000
----------------------------------------
../output/network/negative/article152.gml
Name: article152.gml
Type: MultiDiGraph
Number of nodes: 78
Number of edges: 67
Average in degree:   0.8590
Average out degree:   0.8590
----------------------------------------
../output/network/negative/article2308.gml
Name: article2308.gml
Type: MultiDiGraph
Number of nodes: 66
Number of edges: 56
Average in degree:   0.8485
Average out degree:   0.8485
----------------------------------------
../output/network/negative/article3335.gml
Name: article3335.gml
Type: MultiDiGraph
Number of nodes: 120
Number of edges: 128
Average in degree:   1.0667
Average out degree:   1.0667
----------------------------------------
../output/network/negative/article4106.gml
Name: article4106.gml
Type: MultiDiGraph
Number of nodes: 38
Number of edges: 36
Average in degree:   0.9474
Average out degree:   0.9474
----------------------------------------
../output/network/negative/article432.gml
Name: article432.gml
Type: MultiDiGraph
Number of nodes: 100
Number of edges: 96
Average in degree:   0.9600
Average out degree:   0.9600
----------------------------------------
../output/network/negative/article5164.gml
Name: article5164.gml
Type: MultiDiGraph
Number of nodes: 104
Number of edges: 119
Average in degree:   1.1442
Average out degree:   1.1442
----------------------------------------
../output/network/negative/article5717.gml
Name: article5717.gml
Type: MultiDiGraph
Number of nodes: 62
Number of edges: 62
Average in degree:   1.0000
Average out degree:   1.0000
----------------------------------------
../output/network/negative/article5813.gml
Name: article5813.gml
Type: MultiDiGraph
Number of nodes: 50
Number of edges: 54
Average in degree:   1.0800
Average out degree:   1.0800
----------------------------------------
../output/network/negative/article621.gml
Name: article621.gml
Type: MultiDiGraph
Number of nodes: 30
Number of edges: 32
Average in degree:   1.0667
Average out degree:   1.0667
----------------------------------------
../output/network/negative/article683.gml
Name: article683.gml
Type: MultiDiGraph
Number of nodes: 234
Number of edges: 236
Average in degree:   1.0085
Average out degree:   1.0085
----------------------------------------
../output/network/negative/article703.gml
Name: article703.gml
Type: MultiDiGraph
Number of nodes: 282
Number of edges: 280
Average in degree:   0.9929
Average out degree:   0.9929
----------------------------------------
../output/network/negative/article774.gml
Name: article774.gml
Type: MultiDiGraph
Number of nodes: 57
Number of edges: 54
Average in degree:   0.9474
Average out degree:   0.9474
----------------------------------------
../output/network/negative/article782.gml
Name: article782.gml
Type: MultiDiGraph
Number of nodes: 84
Number of edges: 77
Average in degree:   0.9167
Average out degree:   0.9167
----------------------------------------
../output/network/negative/article99.gml
Name: article99.gml
Type: MultiDiGraph
Number of nodes: 45
Number of edges: 46
Average in degree:   1.0222
Average out degree:   1.0222
----------------------------------------
../output/network/neutral/article2047.gml
Name: article2047.gml
Type: MultiDiGraph
Number of nodes: 52
Number of edges: 61
Average in degree:   1.1731
Average out degree:   1.1731
----------------------------------------
../output/network/neutral/article532.gml
Name: article532.gml
Type: MultiDiGraph
Number of nodes: 51
Number of edges: 37
Average in degree:   0.7255
Average out degree:   0.7255
----------------------------------------
../output/network/neutral/article54.gml
Name: article54.gml
Type: MultiDiGraph
Number of nodes: 48
Number of edges: 37
Average in degree:   0.7708
Average out degree:   0.7708
----------------------------------------
../output/network/neutral/article63.gml
Name: article63.gml
Type: MultiDiGraph
Number of nodes: 17
Number of edges: 15
Average in degree:   0.8824
Average out degree:   0.8824
----------------------------------------
../output/network/neutral/article647.gml
Name: article647.gml
Type: MultiDiGraph
Number of nodes: 54
Number of edges: 48
Average in degree:   0.8889
Average out degree:   0.8889
----------------------------------------
../output/network/neutral/article756.gml
Name: article756.gml
Type: MultiDiGraph
Number of nodes: 41
Number of edges: 40
Average in degree:   0.9756
Average out degree:   0.9756
----------------------------------------
../output/network/positive/article02.gml
Name: article02.gml
Type: MultiDiGraph
Number of nodes: 36
Number of edges: 31
Average in degree:   0.8611
Average out degree:   0.8611
----------------------------------------
../output/network/positive/article1105.gml
Name: article1105.gml
Type: MultiDiGraph
Number of nodes: 38
Number of edges: 31
Average in degree:   0.8158
Average out degree:   0.8158
----------------------------------------
../output/network/positive/article111.gml
Name: article111.gml
Type: MultiDiGraph
Number of nodes: 83
Number of edges: 75
Average in degree:   0.9036
Average out degree:   0.9036
----------------------------------------
../output/network/positive/article1542.gml
Name: article1542.gml
Type: MultiDiGraph
Number of nodes: 45
Number of edges: 51
Average in degree:   1.1333
Average out degree:   1.1333
----------------------------------------
../output/network/positive/article1804.gml
Name: article1804.gml
Type: MultiDiGraph
Number of nodes: 42
Number of edges: 50
Average in degree:   1.1905
Average out degree:   1.1905
----------------------------------------
../output/network/positive/article2.gml
Name: article2.gml
Type: MultiDiGraph
Number of nodes: 28
Number of edges: 23
Average in degree:   0.8214
Average out degree:   0.8214
----------------------------------------
../output/network/positive/article29.gml
Name: article29.gml
Type: MultiDiGraph
Number of nodes: 74
Number of edges: 61
Average in degree:   0.8243
Average out degree:   0.8243
----------------------------------------
../output/network/positive/article30.gml
Name: article30.gml
Type: MultiDiGraph
Number of nodes: 17
Number of edges: 17
Average in degree:   1.0000
Average out degree:   1.0000
----------------------------------------
../output/network/positive/article31.gml
Name: article31.gml
Type: MultiDiGraph
Number of nodes: 48
Number of edges: 43
Average in degree:   0.8958
Average out degree:   0.8958
----------------------------------------
../output/network/positive/article36.gml
Name: article36.gml
Type: MultiDiGraph
Number of nodes: 15
Number of edges: 12
Average in degree:   0.8000
Average out degree:   0.8000
----------------------------------------
../output/network/positive/article37.gml
Name: article37.gml
Type: MultiDiGraph
Number of nodes: 21
Number of edges: 28
Average in degree:   1.3333
Average out degree:   1.3333
----------------------------------------
../output/network/positive/article4150.gml
Name: article4150.gml
Type: MultiDiGraph
Number of nodes: 24
Number of edges: 18
Average in degree:   0.7500
Average out degree:   0.7500
----------------------------------------
../output/network/positive/article4210.gml
Name: article4210.gml
Type: MultiDiGraph
Number of nodes: 63
Number of edges: 71
Average in degree:   1.1270
Average out degree:   1.1270
----------------------------------------
../output/network/positive/article4303.gml
Name: article4303.gml
Type: MultiDiGraph
Number of nodes: 24
Number of edges: 19
Average in degree:   0.7917
Average out degree:   0.7917
----------------------------------------
../output/network/positive/article46.gml
Name: article46.gml
Type: MultiDiGraph
Number of nodes: 80
Number of edges: 83
Average in degree:   1.0375
Average out degree:   1.0375
----------------------------------------
../output/network/positive/article5.gml
Name: article5.gml
Type: MultiDiGraph
Number of nodes: 58
Number of edges: 51
Average in degree:   0.8793
Average out degree:   0.8793
----------------------------------------
../output/network/positive/article5077.gml
Name: article5077.gml
Type: MultiDiGraph
Number of nodes: 45
Number of edges: 49
Average in degree:   1.0889
Average out degree:   1.0889
----------------------------------------
../output/network/positive/article609.gml
Name: article609.gml
Type: MultiDiGraph
Number of nodes: 134
Number of edges: 139
Average in degree:   1.0373
Average out degree:   1.0373
----------------------------------------
../output/network/positive/article620.gml
Name: article620.gml
Type: MultiDiGraph
Number of nodes: 76
Number of edges: 68
Average in degree:   0.8947
Average out degree:   0.8947
----------------------------------------
../output/network/positive/article6247.gml
Name: article6247.gml
Type: MultiDiGraph
Number of nodes: 109
Number of edges: 96
Average in degree:   0.8807
Average out degree:   0.8807
----------------------------------------
../output/network/positive/article664.gml
Name: article664.gml
Type: MultiDiGraph
Number of nodes: 29
Number of edges: 27
Average in degree:   0.9310
Average out degree:   0.9310
----------------------------------------
../output/network/positive/article665.gml
Name: article665.gml
Type: MultiDiGraph
Number of nodes: 35
Number of edges: 30
Average in degree:   0.8571
Average out degree:   0.8571
----------------------------------------
../output/network/positive/article828.gml
Name: article828.gml
Type: MultiDiGraph
Number of nodes: 56
Number of edges: 54
Average in degree:   0.9643
Average out degree:   0.9643

















In [5]:



    


network_data



    


















    
Out[5]:










  
    

      
      name
      sentiment
      n nodes
      n edges
      avg degree
      density
      avg deg cent
      avg bet cent
      avg clo cent
      highest degc
      highest betc
      highest cloc
      avg node connect
      deg assort coeff
      avg in-deg
      avg out-deg
      n strong comp
      n weak comp
      n conn comp
      Gc size
    

  
  
    

      0
      article03.gml
      negative
      18
      13
      1.4444
      0.0425
      0.0850
      0.0025
      0.0480
      (parents, 0.176470588235)
      (immune system, 0.0147058823529)
      (parents, 0.210084033613)
      0.0686
      NaN
      0.7222
      0.7222
      18
      5
      5
      6
    

    

      1
      article05.gml
      negative
      22
      25
      2.2727
      0.0541
      0.1082
      0.0010
      0.0558
      (Jim Carrey, 0.333333333333)
      (mandatory vaccines, 0.00952380952381)
      (Jim Carrey, 0.321428571429)
      0.0758
      0.1488
      1.1364
      1.1364
      22
      3
      3
      14
    

    

      2
      article06.gml
      negative
      124
      121
      1.9516
      0.0079
      0.0159
      0.0003
      0.0129
      (shingles vaccine, 0.130081300813)
      (shingles vaccine, 0.00739704118353)
      (shingles vaccine, 0.130216802168)
      0.0254
      -0.1979
      0.9758
      0.9758
      122
      10
      10
      62
    

    

      3
      article07.gml
      negative
      56
      57
      2.0357
      0.0185
      0.0370
      0.0024
      0.0338
      (scientific fraud, 0.181818181818)
      (CDC, 0.0276094276094)
      (Rep. Bill Posey, 0.204642166344)
      0.0802
      -0.0986
      1.0179
      1.0179
      55
      3
      3
      39
    

    

      4
      article1.gml
      negative
      140
      147
      2.1000
      0.0076
      0.0151
      0.0001
      0.0099
      (mercury, 0.107913669065)
      (mercury, 0.00280210614117)
      (CDC, 0.106766760505)
      0.0161
      -0.0168
      1.0500
      1.0500
      138
      17
      17
      71
    

    

      5
      article1001.gml
      negative
      134
      134
      2.0000
      0.0075
      0.0150
      0.0002
      0.0111
      (SB 277, 0.157894736842)
      (vaccine damage, 0.00398724082935)
      (SB 277, 0.144760635767)
      0.0212
      -0.2159
      1.0000
      1.0000
      134
      17
      17
      84
    

    

      6
      article1021.gml
      negative
      64
      64
      2.0000
      0.0159
      0.0317
      0.0003
      0.0219
      (SV40, 0.285714285714)
      (SV40, 0.0143369175627)
      (SV40, 0.183006535948)
      0.0335
      -0.2714
      1.0000
      1.0000
      64
      10
      10
      27
    

    

      7
      article152.gml
      negative
      78
      67
      1.7179
      0.0112
      0.0223
      0.0012
      0.0207
      (thimerosal, 0.207792207792)
      (thimerosal, 0.0261449077239)
      (thimerosal, 0.15012987013)
      0.0470
      -0.0241
      0.8590
      0.8590
      78
      17
      17
      35
    

    

      8
      article2308.gml
      negative
      66
      56
      1.6970
      0.0131
      0.0261
      0.0002
      0.0178
      (National Vaccine Injury Compensation Program,...
      (National Vaccine Injury Compensation Program,...
      (National Vaccine Injury Compensation Program,...
      0.0254
      -0.2020
      0.8485
      0.8485
      66
      11
      11
      32
    

    

      9
      article3335.gml
      negative
      120
      128
      2.1333
      0.0090
      0.0179
      0.0004
      0.0172
      (vaccines, 0.210084033613)
      (vaccines, 0.0210084033613)
      (adverse effects, 0.117647058824)
      0.0359
      -0.3449
      1.0667
      1.0667
      119
      8
      8
      77
    

    

      10
      article4106.gml
      negative
      38
      36
      1.8947
      0.0256
      0.0512
      0.0018
      0.0364
      (doctors, 0.189189189189)
      (doctors, 0.021021021021)
      (doctors, 0.182432432432)
      0.0676
      0.1194
      0.9474
      0.9474
      38
      5
      5
      27
    

    

      11
      article432.gml
      negative
      100
      96
      1.9200
      0.0097
      0.0194
      0.0002
      0.0123
      (measles death, 0.0808080808081)
      (measles, 0.00566893424036)
      (Baby Boomers, 0.0707070707071)
      0.0217
      -0.1313
      0.9600
      0.9600
      98
      16
      16
      45
    

    

      12
      article5164.gml
      negative
      104
      119
      2.2885
      0.0111
      0.0222
      0.0026
      0.0288
      (children, 0.155339805825)
      (children, 0.049519322292)
      (narcolepsy, 0.162274618585)
      0.0982
      -0.0465
      1.1442
      1.1442
      95
      4
      4
      92
    

    

      13
      article5717.gml
      negative
      62
      62
      2.0000
      0.0164
      0.0328
      0.0001
      0.0184
      (vaccines, 0.131147540984)
      (lemming society, 0.00218579234973)
      (herd mentality, 0.0983606557377)
      0.0241
      -0.0661
      1.0000
      1.0000
      62
      9
      9
      28
    

    

      14
      article5813.gml
      negative
      50
      54
      2.1600
      0.0220
      0.0441
      0.0015
      0.0354
      (Nichole Rolfe, 0.367346938776)
      (Nichole Rolfe, 0.0246598639456)
      (Nichole Rolfe, 0.427394034537)
      0.0690
      -0.1555
      1.0800
      1.0800
      49
      3
      3
      46
    

    

      15
      article621.gml
      negative
      30
      32
      2.1333
      0.0368
      0.0736
      0.0007
      0.0396
      (Surgeon General Vivek Murthy, 0.344827586207)
      (government propaganda, 0.00738916256158)
      (Surgeon General Vivek Murthy, 0.287356321839)
      0.0563
      -0.0182
      1.0667
      1.0667
      30
      4
      4
      22
    

    

      16
      article683.gml
      negative
      234
      236
      2.0171
      0.0043
      0.0087
      0.0002
      0.0091
      (thimerosal, 0.103004291845)
      (hepatitis B vaccine, 0.0102856297173)
      (hepatitis B vaccine, 0.0936960035672)
      0.0224
      -0.0660
      1.0085
      1.0085
      231
      31
      31
      140
    

    

      17
      article703.gml
      negative
      282
      280
      1.9858
      0.0035
      0.0071
      0.0000
      0.0060
      (vaccines, 0.0782918149466)
      (vaccines, 0.0030757498729)
      (drug companies, 0.0614946619217)
      0.0115
      -0.1909
      0.9929
      0.9929
      274
      40
      40
      86
    

    

      18
      article774.gml
      negative
      57
      54
      1.8947
      0.0169
      0.0338
      0.0007
      0.0204
      (encephalopathy, 0.125)
      (autism, 0.0103896103896)
      (government, 0.0972222222222)
      0.0363
      0.0014
      0.9474
      0.9474
      54
      10
      10
      19
    

    

      19
      article782.gml
      negative
      84
      77
      1.8333
      0.0110
      0.0221
      0.0001
      0.0142
      (measles, 0.144578313253)
      (measles, 0.00352630032324)
      (children with ASD, 0.132530120482)
      0.0208
      -0.2281
      0.9167
      0.9167
      84
      10
      10
      29
    

    

      20
      article99.gml
      negative
      45
      46
      2.0444
      0.0232
      0.0465
      0.0018
      0.0448
      (thimerosal, 0.431818181818)
      (thimerosal, 0.0502114164905)
      (thimerosal, 0.356719367589)
      0.0818
      -0.3927
      1.0222
      1.0222
      43
      4
      4
      32
    

    

      21
      article2047.gml
      neutral
      52
      61
      2.3462
      0.0230
      0.0460
      0.0022
      0.0483
      (SB277, 0.509803921569)
      (SB277, 0.0701960784314)
      (SB277, 0.340413943355)
      0.1007
      -0.2046
      1.1731
      1.1731
      50
      5
      5
      39
    

    

      22
      article532.gml
      neutral
      51
      37
      1.4510
      0.0145
      0.0290
      0.0002
      0.0172
      (acellular pertussis vaccine, 0.14)
      (acellular pertussis vaccine, 0.00571428571429)
      (acellular pertussis vaccine, 0.098)
      0.0227
      -0.0407
      0.7255
      0.7255
      50
      16
      16
      11
    

    

      23
      article54.gml
      neutral
      48
      37
      1.5417
      0.0164
      0.0328
      0.0002
      0.0187
      (pertussis vaccine, 0.148936170213)
      (pertussis vaccine, 0.00416281221092)
      (pertussis, 0.0851063829787)
      0.0239
      -0.1324
      0.7708
      0.7708
      48
      12
      12
      8
    

    

      24
      article63.gml
      neutral
      17
      15
      1.7647
      0.0551
      0.1103
      0.0032
      0.0738
      (high-dose flu vaccine, 0.6875)
      (high-dose flu vaccine, 0.0458333333333)
      (high-dose flu vaccine, 0.630208333333)
      0.0993
      -0.1094
      0.8824
      0.8824
      17
      2
      2
      15
    

    

      25
      article647.gml
      neutral
      54
      48
      1.7778
      0.0168
      0.0335
      0.0003
      0.0190
      (Dwoskin Family Foundation, 0.150943396226)
      (Generation Rescue, 0.00507982583454)
      (Dwoskin Family Foundation, 0.152830188679)
      0.0255
      -0.0176
      0.8889
      0.8889
      54
      11
      11
      12
    

    

      26
      article756.gml
      neutral
      41
      40
      1.9512
      0.0244
      0.0488
      0.0005
      0.0303
      (vaccines, 0.25)
      (anti-vaccine movement, 0.00608974358974)
      (vaccines, 0.2)
      0.0439
      -0.2470
      0.9756
      0.9756
      40
      6
      6
      18
    

    

      27
      article02.gml
      positive
      36
      31
      1.7222
      0.0246
      0.0492
      0.0003
      0.0260
      (vaccinations, 0.142857142857)
      (religion, 0.00252100840336)
      (vaccinations, 0.142857142857)
      0.0333
      0.0359
      0.8611
      0.8611
      36
      9
      9
      8
    

    

      28
      article1105.gml
      positive
      38
      31
      1.6316
      0.0220
      0.0441
      0.0004
      0.0257
      (parents who refuse to vaccinate their childre...
      (parents who refuse to vaccinate their childre...
      (parents, 0.172119487909)
      0.0356
      0.0889
      0.8158
      0.8158
      37
      10
      10
      14
    

    

      29
      article111.gml
      positive
      83
      75
      1.8072
      0.0110
      0.0220
      0.0003
      0.0149
      (herd immunity, 0.0731707317073)
      (measles vaccination rate, 0.00301114122252)
      (measles virus, 0.0548780487805)
      0.0270
      -0.1159
      0.9036
      0.9036
      83
      13
      13
      25
    

    

      30
      article1542.gml
      positive
      45
      51
      2.2667
      0.0258
      0.0515
      0.0035
      0.0526
      (HPV vaccine, 0.363636363636)
      (HPV vaccine, 0.0687984496124)
      (HPV vaccine, 0.284090909091)
      0.1177
      -0.3533
      1.1333
      1.1333
      45
      5
      5
      34
    

    

      31
      article1804.gml
      positive
      42
      50
      2.3810
      0.0290
      0.0581
      0.0011
      0.0389
      (Gardasil, 0.268292682927)
      (Gardasil, 0.019512195122)
      (girls, 0.15243902439)
      0.0685
      0.0897
      1.1905
      1.1905
      41
      6
      6
      27
    

    

      32
      article2.gml
      positive
      28
      23
      1.6429
      0.0304
      0.0608
      0.0006
      0.0330
      (decrease in exemption rates, 0.222222222222)
      (decrease in exemption rates, 0.00712250712251)
      (decrease in exemption rates, 0.185185185185)
      0.0410
      0.0631
      0.8214
      0.8214
      28
      7
      7
      9
    

    

      33
      article29.gml
      positive
      74
      61
      1.6486
      0.0113
      0.0226
      0.0001
      0.0138
      (Tdap vaccine, 0.123287671233)
      (Tdap vaccine, 0.00437595129376)
      (polio, 0.0872386445566)
      0.0183
      -0.2339
      0.8243
      0.8243
      72
      17
      17
      16
    

    

      34
      article30.gml
      positive
      17
      17
      2.0000
      0.0625
      0.1250
      0.0010
      0.0617
      (vaccines, 0.5625)
      (minor symptoms, 0.0166666666667)
      (vaccines, 0.4375)
      0.0699
      0.2917
      1.0000
      1.0000
      17
      2
      2
      15
    

    

      35
      article31.gml
      positive
      48
      43
      1.7917
      0.0191
      0.0381
      0.0011
      0.0231
      (autism risk, 0.170212765957)
      (autism, 0.0115633672525)
      (MMR vaccine, 0.0851063829787)
      0.0421
      0.3114
      0.8958
      0.8958
      48
      10
      10
      24
    

    

      36
      article36.gml
      positive
      15
      12
      1.6000
      0.0571
      0.1143
      0.0044
      0.0809
      (2014-2015 FLULAVAL QUADRIVALENT flu vaccine, ...
      (2014-2015 FLULAVAL QUADRIVALENT flu vaccine, ...
      (2014-2015 FLULAVAL QUADRIVALENT flu vaccine, ...
      0.1143
      -0.3581
      0.8000
      0.8000
      14
      4
      4
      8
    

    

      37
      article37.gml
      positive
      21
      28
      2.6667
      0.0667
      0.1333
      0.0015
      0.0697
      (HPV vaccine, 0.4)
      (multi-site protection, 0.0144736842105)
      (HPV vaccine, 0.35)
      0.1000
      -0.2305
      1.3333
      1.3333
      21
      2
      2
      19
    

    

      38
      article4150.gml
      positive
      24
      18
      1.5000
      0.0326
      0.0652
      0.0002
      0.0343
      (vaccines do not cause autism, 0.173913043478)
      (MMR vaccine-autism link, 0.00592885375494)
      (studies, 0.130434782609)
      0.0380
      -0.3842
      0.7500
      0.7500
      24
      6
      6
      7
    

    

      39
      article4210.gml
      positive
      63
      71
      2.2540
      0.0182
      0.0364
      0.0009
      0.0267
      (Jain study, 0.241935483871)
      (Jain study, 0.0137493389741)
      (Jain study, 0.244959677419)
      0.0515
      -0.1602
      1.1270
      1.1270
      63
      2
      2
      54
    

    

      40
      article4303.gml
      positive
      24
      19
      1.5833
      0.0344
      0.0688
      0.0002
      0.0353
      (anti-vaxxer, 0.217391304348)
      (high risk children, 0.00197628458498)
      (anti-vaxxer, 0.217391304348)
      0.0399
      -0.2799
      0.7917
      0.7917
      24
      6
      6
      6
    

    

      41
      article46.gml
      positive
      80
      83
      2.0750
      0.0131
      0.0263
      0.0014
      0.0325
      (meningococcal disease, 0.354430379747)
      (meningococcal disease, 0.0548523206751)
      (meningococcal disease, 0.2194092827)
      0.0744
      -0.3162
      1.0375
      1.0375
      78
      9
      9
      53
    

    

      42
      article5.gml
      positive
      58
      51
      1.7586
      0.0154
      0.0309
      0.0002
      0.0184
      (measles, 0.157894736842)
      (measles, 0.00438596491228)
      (parents, 0.143274853801)
      0.0251
      -0.1960
      0.8793
      0.8793
      58
      10
      10
      23
    

    

      43
      article5077.gml
      positive
      45
      49
      2.1778
      0.0247
      0.0495
      0.0018
      0.0361
      (measles vaccine, 0.227272727273)
      (immune system, 0.0174418604651)
      (children, 0.168414918415)
      0.0717
      -0.1655
      1.0889
      1.0889
      44
      5
      5
      34
    

    

      44
      article609.gml
      positive
      134
      139
      2.0746
      0.0078
      0.0156
      0.0008
      0.0153
      (religious groups, 0.127819548872)
      (religious groups, 0.0257461836409)
      (religious groups, 0.141003192914)
      0.0426
      -0.2103
      1.0373
      1.0373
      127
      22
      22
      60
    

    

      45
      article620.gml
      positive
      76
      68
      1.7895
      0.0119
      0.0239
      0.0001
      0.0134
      (states, 0.0933333333333)
      (states, 0.0027027027027)
      (state-level policies, 0.0568888888889)
      0.0198
      0.3044
      0.8947
      0.8947
      76
      16
      16
      33
    

    

      46
      article6247.gml
      positive
      109
      96
      1.7615
      0.0082
      0.0163
      0.0000
      0.0089
      (anti-vaccine website, 0.12962962963)
      (MMR vaccine-autism link, 0.00103842159917)
      (anti-vaccine website, 0.12962962963)
      0.0115
      -0.3036
      0.8807
      0.8807
      109
      16
      16
      24
    

    

      47
      article664.gml
      positive
      29
      27
      1.8621
      0.0333
      0.0665
      0.0012
      0.0395
      (measles vaccine, 0.285714285714)
      (measles infections, 0.00925925925926)
      (measles vaccine, 0.21875)
      0.0567
      -0.2007
      0.9310
      0.9310
      26
      5
      5
      9
    

    

      48
      article665.gml
      positive
      35
      30
      1.7143
      0.0252
      0.0504
      0.0009
      0.0310
      (rubella, 0.147058823529)
      (rubella virus, 0.0106951871658)
      (rubella, 0.147058823529)
      0.0479
      0.0248
      0.8571
      0.8571
      35
      7
      7
      12
    

    

      49
      article828.gml
      positive
      56
      54
      1.9286
      0.0175
      0.0351
      0.0012
      0.0372
      (SB 277, 0.381818181818)
      (SB 277, 0.0464646464646)
      (SB 277, 0.222727272727)
      0.0679
      -0.2407
      0.9643
      0.9643
      54
      7
      7
      38
    

  




















In [6]:



    


# save dataframe to csv
network_data.to_csv('network_df', encoding = 'utf-8')



    











In [ ]:



    






    











In [ ]:



    






    











In [ ]:



    






    











In [ ]:

single network graph calculations

need to update this from: single_calc.ipynb





In [ ]:



    


# for individual network

graph = nx.read_gml('../output/network/negative/article03.gml')
ugraph = graph.to_undirected()
U = graph.to_undirected(reciprocal=True)
e = U.edges()
ugraph.add_edges_from(e)
print nx.info(graph)
print nx.info(ugraph)



    











In [ ]:



    


# degree histogram: returns a list of frequencies of degree values
nx.degree_histogram(graph)



    











In [ ]:



    


# degree centrality
a = nx.degree_centrality(graph)
dfIn=pd.DataFrame.from_dict(a,orient='index')
dfIn.columns = ['degree centrality']
dfIn = dfIn.sort_values(by=['degree centrality'])
dfIn



    











In [ ]:



    


# betweenness centrality
a = nx.betweenness_centrality(graph)
dfIn=pd.DataFrame.from_dict(a,orient='index')
dfIn.columns = ['betweenness centrality']
dfIn = dfIn.sort_values(by=['betweenness centrality'])
dfIn



    











In [ ]:



    


# closeness centrality
a = nx.closeness_centrality(graph)
dfIn=pd.DataFrame.from_dict(a,orient='index')
dfIn.columns = ['closeness centrality']
dfIn = dfIn.sort_values(by=['closeness centrality'])
dfIn



    











In [ ]:



    


# in degree centrality
a = nx.in_degree_centrality(graph)
dfIn=pd.DataFrame.from_dict(a,orient='index')
dfIn.columns = ['in deg centrality']
dfIn = dfIn.sort_values(by=['in deg centrality'])
dfIn



    











In [ ]:



    


# out degree centrality
b = nx.out_degree_centrality(graph)
dfIn=pd.DataFrame.from_dict(b,orient='index')
dfIn.columns = ['out deg centrality']
dfIn = dfIn.sort_values(by=['out deg centrality'])
dfIn

Content source: gloriakang/vax-sentiment

Similar notebooks:

notebook.community | gallery | about